We consider a multi-agent episodic MDP setup where an agent (leader) takes action at each step of the episode followed by another agent (follower). The state evolution and rewards depend on the joint action pair of the leader and the follower. Such type of interactions can find applications in many domains such as smart grids, mechanism design, security, and policymaking. We are interested in how to learn policies for both the players with provable performance guarantee under a bandit feedback setting. We focus on a setup where both the leader and followers are {\em non-myopic}, i.e., they both seek to maximize their rewards over the entire episode and consider a linear MDP which can model continuous state-space which is very common in many RL applications. We propose a {\em model-free} RL algorithm and show that $\tilde{\mathcal{O}}(\sqrt{d^3H^3T})$ regret bounds can be achieved for both the leader and the follower, where $d$ is the dimension of the feature mapping, $H$ is the length of the episode, and $T$ is the total number of steps under the bandit feedback information setup. Thus, our result holds even when the number of states becomes infinite. The algorithm relies on {\em novel} adaptation of the LSVI-UCB algorithm. Specifically, we replace the standard greedy policy (as the best response) with the soft-max policy for both the leader and the follower. This turns out to be key in establishing uniform concentration bound for the value functions. To the best of our knowledge, this is the first sub-linear regret bound guarantee for the Markov games with non-myopic followers with function approximation.

我们研究了受限的强化学习问题，其中代理的目的是最大程度地提高预期的累积奖励，从而受到对实用程序函数的预期总价值的约束。与现有的基于模型的方法或无模型方法伴随着“模拟器”，我们旨在开发第一个无模型的无模拟算法，即使在大规模系统中，也能够实现sublinear遗憾和透明度的约束侵犯。为此，我们考虑具有线性函数近似的情节约束决策过程，其中过渡动力学和奖励函数可以表示为某些已知功能映射的线性函数。我们表明$ \ tilde {\ mathcal {o}}（\ sqrt {d^3h^3t}）$遗憾和$ \ tilde {\ tillcal {\ mathcal {o}}（\ sqrt {d^3h^3ht}）$约束$约束$约束可以实现违规范围，其中$ d $是功能映射的尺寸，$ h $是情节的长度，而$ t $是总数的总数。我们的界限是在没有明确估计未知过渡模型或需要模拟器的情况下达到的，并且仅通过特征映射的维度依赖于状态空间。因此，即使国家的数量进入无穷大，我们的界限也会存在。我们的主要结果是通过标准LSVI-UCB算法的新型适应来实现的。特别是，我们首先将原始二次优化引入LSVI-UCB算法中，以在遗憾和违反约束之间取得平衡。更重要的是，我们使用软马克斯政策取代了LSVI-UCB中的状态行动功能的标准贪婪选择。事实证明，这对于通过其近似平滑度的权衡来确定受约束案例的统一浓度是关键。我们还表明，一个人可以达到均匀的约束违规行为，同时仍然保持相同的订单相对于$ t $。

Cashews are grown by over 3 million smallholders in more than 40 countries worldwide as a principal source of income. As the third largest cashew producer in Africa, Benin has nearly 200,000 smallholder cashew growers contributing 15% of the country's national export earnings. However, a lack of information on where and how cashew trees grow across the country hinders decision-making that could support increased cashew production and poverty alleviation. By leveraging 2.4-m Planet Basemaps and 0.5-m aerial imagery, newly developed deep learning algorithms, and large-scale ground truth datasets, we successfully produced the first national map of cashew in Benin and characterized the expansion of cashew plantations between 2015 and 2021. In particular, we developed a SpatioTemporal Classification with Attention (STCA) model to map the distribution of cashew plantations, which can fully capture texture information from discriminative time steps during a growing season. We further developed a Clustering Augmented Self-supervised Temporal Classification (CASTC) model to distinguish high-density versus low-density cashew plantations by automatic feature extraction and optimized clustering. Results show that the STCA model has an overall accuracy of 80% and the CASTC model achieved an overall accuracy of 77.9%. We found that the cashew area in Benin has doubled from 2015 to 2021 with 60% of new plantation development coming from cropland or fallow land, while encroachment of cashew plantations into protected areas has increased by 70%. Only half of cashew plantations were high-density in 2021, suggesting high potential for intensification. Our study illustrates the power of combining high-resolution remote sensing imagery and state-of-the-art deep learning algorithms to better understand tree crops in the heterogeneous smallholder landscape.

Logic Mill is a scalable and openly accessible software system that identifies semantically similar documents within either one domain-specific corpus or multi-domain corpora. It uses advanced Natural Language Processing (NLP) techniques to generate numerical representations of documents. Currently it leverages a large pre-trained language model to generate these document representations. The system focuses on scientific publications and patent documents and contains more than 200 million documents. It is easily accessible via a simple Application Programming Interface (API) or via a web interface. Moreover, it is continuously being updated and can be extended to text corpora from other domains. We see this system as a general-purpose tool for future research applications in the social sciences and other domains.

Multiple studies have focused on predicting the prospective popularity of an online document as a whole, without paying attention to the contributions of its individual parts. We introduce the task of proactively forecasting popularities of sentences within online news documents solely utilizing their natural language content. We model sentence-specific popularity forecasting as a sequence regression task. For training our models, we curate InfoPop, the first dataset containing popularity labels for over 1.7 million sentences from over 50,000 online news documents. To the best of our knowledge, this is the first dataset automatically created using streams of incoming search engine queries to generate sentence-level popularity annotations. We propose a novel transfer learning approach involving sentence salience prediction as an auxiliary task. Our proposed technique coupled with a BERT-based neural model exceeds nDCG values of 0.8 for proactive sentence-specific popularity forecasting. Notably, our study presents a non-trivial takeaway: though popularity and salience are different concepts, transfer learning from salience prediction enhances popularity forecasting. We release InfoPop and make our code publicly available: https://github.com/sayarghoshroy/InfoPopularity

Learning policies from fixed offline datasets is a key challenge to scale up reinforcement learning (RL) algorithms towards practical applications. This is often because off-policy RL algorithms suffer from distributional shift, due to mismatch between dataset and the target policy, leading to high variance and over-estimation of value functions. In this work, we propose variance regularization for offline RL algorithms, using stationary distribution corrections. We show that by using Fenchel duality, we can avoid double sampling issues for computing the gradient of the variance regularizer. The proposed algorithm for offline variance regularization (OVAR) can be used to augment any existing offline policy optimization algorithms. We show that the regularizer leads to a lower bound to the offline policy optimization objective, which can help avoid over-estimation errors, and explains the benefits of our approach across a range of continuous control domains when compared to existing state-of-the-art algorithms.

Several self-supervised representation learning methods have been proposed for reinforcement learning (RL) with rich observations. For real-world applications of RL, recovering underlying latent states is crucial, particularly when sensory inputs contain irrelevant and exogenous information. In this work, we study how information bottlenecks can be used to construct latent states efficiently in the presence of task-irrelevant information. We propose architectures that utilize variational and discrete information bottlenecks, coined as RepDIB, to learn structured factorized representations. Exploiting the expressiveness bought by factorized representations, we introduce a simple, yet effective, bottleneck that can be integrated with any existing self-supervised objective for RL. We demonstrate this across several online and offline RL benchmarks, along with a real robot arm task, where we find that compressed representations with RepDIB can lead to strong performance improvements, as the learned bottlenecks help predict only the relevant state while ignoring irrelevant information.

We present a machine-learning framework to accurately characterize morphologies of Active Galactic Nucleus (AGN) host galaxies within $z<1$. We first use PSFGAN to decouple host galaxy light from the central point source, then we invoke the Galaxy Morphology Network (GaMorNet) to estimate whether the host galaxy is disk-dominated, bulge-dominated, or indeterminate. Using optical images from five bands of the HSC Wide Survey, we build models independently in three redshift bins: low $(0<z<0.25)$, medium $(0.25<z<0.5)$, and high $(0.5<z<1.0)$. By first training on a large number of simulated galaxies, then fine-tuning using far fewer classified real galaxies, our framework predicts the actual morphology for $\sim$ $60\%-70\%$ host galaxies from test sets, with a classification precision of $\sim$ $80\%-95\%$, depending on redshift bin. Specifically, our models achieve disk precision of $96\%/82\%/79\%$ and bulge precision of $90\%/90\%/80\%$ (for the 3 redshift bins), at thresholds corresponding to indeterminate fractions of $30\%/43\%/42\%$. The classification precision of our models has a noticeable dependency on host galaxy radius and magnitude. No strong dependency is observed on contrast ratio. Comparing classifications of real AGNs, our models agree well with traditional 2D fitting with GALFIT. The PSFGAN+GaMorNet framework does not depend on the choice of fitting functions or galaxy-related input parameters, runs orders of magnitude faster than GALFIT, and is easily generalizable via transfer learning, making it an ideal tool for studying AGN host galaxy morphology in forthcoming large imaging survey.

Speech systems are sensitive to accent variations. This is especially challenging in the Indian context, with an abundance of languages but a dearth of linguistic studies characterising pronunciation variations. The growing number of L2 English speakers in India reinforces the need to study accents and L1-L2 interactions. We investigate the accents of Indian English (IE) speakers and report in detail our observations, both specific and common to all regions. In particular, we observe the phonemic variations and phonotactics occurring in the speakers' native languages and apply this to their English pronunciations. We demonstrate the influence of 18 Indian languages on IE by comparing the native language pronunciations with IE pronunciations obtained jointly from existing literature studies and phonetically annotated speech of 80 speakers. Consequently, we are able to validate the intuitions of Indian language influences on IE pronunciations by justifying pronunciation rules from the perspective of Indian language phonology. We obtain a comprehensive description in terms of universal and region-specific characteristics of IE, which facilitates accent conversion and adaptation of existing ASR and TTS systems to different Indian accents.

A hallmark of human intelligence is the ability to learn new concepts purely from language. Several recent approaches have explored training machine learning models via natural language supervision. However, these approaches fall short in leveraging linguistic quantifiers (such as 'always' or 'rarely') and mimicking humans in compositionally learning complex tasks. Here, we present LaSQuE, a method that can learn zero-shot classifiers from language explanations by using three new strategies - (1) modeling the semantics of linguistic quantifiers in explanations (including exploiting ordinal strength relationships, such as 'always' > 'likely'), (2) aggregating information from multiple explanations using an attention-based mechanism, and (3) model training via curriculum learning. With these strategies, LaSQuE outperforms prior work, showing an absolute gain of up to 7% in generalizing to unseen real-world classification tasks.